Triton Inference Server

NVIDIA

Container

NVIDIA

Triton Inference Server

Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.

NVIDIA AI Enterprise Supported

Layer	Label		Created
17ab53dd52e741e334ea15bc2af1454edc6e94516faa2abd9f90dd7d93983201	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace`	01/27/2026 10:13 PM UTC
5a790ab9c44b6534f507c242e81eb4fa716f81a676e3e1dcee85073be24ea3b4	ENV	`LD_LIBRARY_PATH=/opt/hpcx/ompi/lib:/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64`	01/27/2026 10:13 PM UTC
b2822d4e5380c663c4e7bd8388ee1621a87f95e6d619f1edd8eacd32fc4387a7	ENV	`LD_LIBRARY_PATH=/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64`	01/27/2026 10:13 PM UTC
b57ea8f1ca9ac1c6555da705410a0e2ca39a7fe9d96d6fb997546e6b49cce401	ENV	`PATH=/workspace/install/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin`	01/27/2026 10:13 PM UTC
73d1be1635495f9ade8015cc01205aa8d4f9113880b30c4a73bd81f1a2dac318	ENV	`NVIDIA_BUILD_ID=259402044`	01/27/2026 10:13 PM UTC
e21b81bf712e833a13ad5238180cac8c2eb5b5201486da5f50bd1fc0e9083181	ENV	`NVIDIA_TRITON_SERVER_SDK_VERSION=26.01`	01/27/2026 10:13 PM UTC
9b9dfead90d531d247c13fc269d20a779e9a06a18f04228ba74eb7fc612c19be	ARG	`NVIDIA_BUILD_ID=259402044`	01/27/2026 10:13 PM UTC
e3bc76cce53f4d0521a0e6b68643c66bd387658e55eab7a14a32c7aad8659b52	ARG	`NVIDIA_TRITON_SERVER_SDK_VERSION=26.01`	01/27/2026 10:13 PM UTC
11e5f1fe7bb2fc24c88ad1aab748f2278e3782b9824eecf89070e68b8e3da938	RUN	DCGM_VERSION=4.4.2-1 TRITON_REPO_ORGANIZATION=https://github.com/triton-inference-server TRITON_CORE_REPO_TAG=r26.01 TARGETPLATFORM=linux/arm64 TRITON_ENABLE_GPU=ON TRITON_MODEL_ANALYZER_REPO_TAG=r26.01 TRITON_MODEL_ANALYZER_REPO=https://github.com/triton-inference-server/model_analyzer@r26.01 sed 's/Server/Server SDK/' /opt/nvidia/entrypoint.d/10-banner.txt \| sed 's/^===/=======/' > /opt/nvidia/entrypoint.d/10-banner.new && mv /opt/nvidia/entrypoint.d/10-banner.new /opt/nvidia/entrypoint.d/10-banner.txt	01/27/2026 10:13 PM UTC
20ef96747c08b839d10201e1f28b5cd98ce67ae8fd5fb23760f2fbf1fc006096	COPY	`docker/entrypoint.d/ /opt/nvidia/entrypoint.d/`	01/27/2026 10:13 PM UTC